ABSTRACT
Though I am not an expert in the field of artificial intelligence (AI) safety, I'm not that far from it. As a mathematician and University of California, Berkeley professor, I have been exposed over the years to various topics in computer science pertinent to AI. Although my current research is on the Langlands program, on the interface of math and quantum physics (see References 1 and 2), when I was a college student I was enrolled in an applied mathematics program that involved quite a bit of computer science and applied math. My first research projects were in fact on the development of decision-making algorithms in medical diagnostics (see Reference 2, Chapter 12), and I have retained interest in topics such as data analysis and machine learning.
